A 753B model reads the problem: A 4B model writes the answer.
Mostik reports that its latent bridge lets the 4B model close half the performance gap to the 753B model
The bridged pair uses 2.5x less compute than a score-matched mid-sized model
A fascinating alternative to the text-based handoffs used by most multi-model systems today. Incredible!
meet @mostik_ai! what happens when you put 12 PhDs in one room for four months? first place on the ARC-AGI leaderboard, which I can't say much about while the c...